Theoretically Expressive and Edge-aware Graph Learning

Federico Errica; Davide Bacciu; Alessio Micheli

Theoretically Expressive and Edge-aware Graph Learning

Machine Learning 2020-01-27 v1 Artificial Intelligence Machine Learning

Authors: Federico Errica , Davide Bacciu , Alessio Micheli

Abstract

We propose a new Graph Neural Network that combines recent advancements in the field. We give theoretical contributions by proving that the model is strictly more general than the Graph Isomorphism Network and the Gated Graph Neural Network, as it can approximate the same functions and deal with arbitrary edge values. Then, we show how a single node information can flow through the graph unchanged.

Keywords

graph generation graph neural network graph representation learning

Cite

@article{arxiv.2001.09005,
  title  = {Theoretically Expressive and Edge-aware Graph Learning},
  author = {Federico Errica and Davide Bacciu and Alessio Micheli},
  journal= {arXiv preprint arXiv:2001.09005},
  year   = {2020}
}

Related papers

View all related →